Speech recognition on board of an aircraft

Patent metadata

Field	Value
Publication number	US-10056085-B2
Application number	US-201615184302-A
Country	US
Kind code	B2
Filing date	Jun 16, 2016
Priority date	Jun 18, 2015
Publication date	Aug 21, 2018
Grant date	Aug 21, 2018

Abstract

A method of performing speech recognition on board an aircraft, a computer program for executing the method, as well as a speech recognition unit for performing speech recognition on board an aircraft. The method comprises receiving a speech signal spoken by a user; performing speaker recognition on the speech signal to identify the user from the speech signal; selecting a speech recognition user profile which is associated with the identified user; and performing speech recognition on the speech signal using the selected user profile.

First claim

The invention claimed is:

1. A method of performing speech recognition on board of an aircraft, comprising:
downloading a plurality of speech recognition profiles from a remote source providing user profiles of airline crew members;
receiving a speech signal spoken by a user being one of the airline crew members;
performing speaker recognition on the speech signal to identify the user from the speech signal;
selecting, among the downloaded plurality of speech recognition profiles, a speech recognition user profile which is associated with the identified user; and
performing speech recognition on the speech signal using the selected user profile;
wherein speaker recognition is performed on a first portion of the speech signal to identify the user and speech recognition is performed using the selected user profile retrospectively beginning from the beginning of the first portion of the speech signal and continuing with a remaining portion of the speech signal;
wherein performing speech recognition comprises converting the speech signal into a text message to be displayed to at least one passenger in a cabin of the aircraft; and
wherein the text message is sent to a passenger-owned device which has established connectivity to an onboard connectivity system.

2. The method of claim 1 , wherein speaker recognition is performed based on speaker recognition data, the speaker recognition data including at least one of voice characteristics of the user, pronunciation characteristics of the user, a vocabulary characteristic to the user, and probabilities of occurrences of at least one of words, phrases and formulations in the language commonly used by the user.

3. The method of claim 2 , wherein the speaker recognition data is updated while performing speech recognition on the speech signal.

4. The method of claim 1 , wherein at least one of speaker recognition and speech recognition is performed based on a vocabulary limited to terms relating to a cabin of the aircraft or situations around the cabin of the aircraft.

5. The method of claim 4 , wherein the vocabulary is specific to at least one of a user and a user group.

6. A non-transitory computer-readable medium storing instructions executable by a computer processor for signaling speech signal related test messages on board an aircraft, comprising instructions to:
receive a speech signal spoken by a user;
download a plurality of speech recognition profiles from a remote source providing user profiles of airline crew members;
perform speaker recognition on the speech signal to identify the user from the speech signal;
select, among the downloaded plurality of speech recognition profiles, a speech recognition user profile which is associated with the identified user; and
perform speech recognition on the speech signal using the selected user profile;
wherein speaker recognition is performed on a first portion of the speech signal to identify the user and speech recognition is performed using the selected user profile retrospectively beginning from the beginning of the first portion of the speech signal and continuing with a remaining portion of the speech signal;
wherein performing speech recognition comprises converting the speech signal into a text message to be displayed to at least one passenger in a cabin of the aircraft; and
wherein the text message is sent to a passenger-owned device which has established connectivity to an onboard connectivity system.

7. A speech recognition unit for performing speech recognition on board of an aircraft, wherein the speech recognition unit comprises:
a downloading component configured to download a plurality of speech recognition profiles from a remote source providing user profiles of airline crew members;
a receiving component configured to receive a speech signal spoken by a user;
a speaker recognition component configured to perform speaker recognition on the speech signal to identify the user from the speech signal;
a selecting component configured to select, among the downloaded plurality of speech recognition profiles, a speech recognition user profile which is associated with the identified user; and
a speech recognition component configured to perform speech recognition on the speech signal using the selected user profile;
wherein speaker recognition is performed on a first portion of the speech signal to identify the user and speech recognition is performed using the selected user profile retrospectively beginning from the beginning of the first portion of the speech signal and continuing with a remaining portion of the speech signal;
wherein performing speech recognition comprises converting the speech signal into a text message to be displayed to at least one passenger in a cabin of the aircraft; and
wherein the text message is sent to a passenger-owned device which has established connectivity to an onboard connectivity system.

Assignees

• Airbus Operations Gmbh

Inventors

• Klose Peter
• Luedtke Michael

Classifications

• G10L17/00

  Speaker identification or verification techniques · CPC title

• B64D11/0015

  Arrangements for entertainment or communications, e.g. radio, television · CPC title

• G10L15/063

  Training · CPC title

• G10L2015/227

  of the speaker; Human-factor methodology · CPC title

• G10L2015/0635

  updating or merging of old and new templates; Mean values; Weighting · CPC title